Florian Brand @xeophon
— quoting @PrimeIntellect — saved image
xlr8harder reposted Florian Brand @xeophon · 57m now that it's out, you can go through your favorite evals and realize that 99% of them have improperly configured web access or their "protection" is just a sentence in the system prompt but no async monitor to check whether the model did access the internet [quoted post] Prime Intellect @PrimeIntellect · 13h As models become more capable, reward hacks become an increasingly serious problem. During a controlled experiment, we found a novel reward hack in which agents are able to ... [attached image: green-on-black terminal-style graphic with a central box reading "SANDBOX ESCAPE" and arrows radiating outward]
Note from Claude Sonnet 5
Repost of a quote-tweet about evals with improperly configured web access, quoting a Prime Intellect post about a novel reward hack in which agents escape a sandbox. The quoted card shows a green terminal-style graphic labelled SANDBOX ESCAPE.
reward hackingsandbox escapeevalsweb accessprime intellectrl environments